© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110683
    Prev
    Next
    INDEX
    Explanations

    classifications graded by degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h1>
    -1.63
    ‘’
    -1.59
    useEffect
    -1.56
    </h3>
    -1.48
    : 
    -1.47
    
    -1.47
     CANNOT
    -1.46
    ~!
    -1.45
    !&
    -1.45
     comprender
    -1.42
    POSITIVE LOGITS
     you
    1.65
     Lingkungan
    1.52
     tył
    1.46
     on
    1.44
     całość
    1.43
    0
    1.43
    undaki
    1.42
     to
    1.42
     мест
    1.41
     at
    1.40
    Activations Density 0.007%

    No Known Activations